summaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAgeFilesLines
* remove extra parenswip-5900Alfredo Deza2013-09-031-1/+1
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* remove python-ceph from debian scriptsAlfredo Deza2013-08-301-14/+1
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* remove python-ceph from ceph.spec.inAlfredo Deza2013-08-301-28/+2
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* remove single file python targets from makefileAlfredo Deza2013-08-291-6/+0
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* add the spec and debian files for rbd packagingAlfredo Deza2013-08-288-0/+103
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* add the spec and debian files for rados packagingAlfredo Deza2013-08-288-0/+103
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* add the spec and debian files for ceph-rest packagingAlfredo Deza2013-08-288-0/+103
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* add the spec and debian files for cephfs packagingAlfredo Deza2013-08-288-0/+103
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* add the spec and debian files for argparse packagingAlfredo Deza2013-08-288-0/+103
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* ceph.in, ceph-rest-api: adapt "run from src/" hack to virtualenvDan Mick2013-08-272-13/+6
| | | | | | | | | 1) change python to the virtualenv version, which means 2) we can avoid setting sys.path directly Also: 3) remove the "DEVELOPER MODE" message Signed-off-by: Dan Mick <dan.mick@inktank.com>
* remove invalid comment in targetAlfredo Deza2013-08-271-1/+0
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* add the targets to the makefile.amAlfredo Deza2013-08-271-13/+21
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* fix the order of the calls to setup.py develop so dependencies are metAlfredo Deza2013-08-221-5/+5
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* create a bootstrap file for pybindAlfredo Deza2013-08-221-0/+60
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* remove argparse from ceph-rest, fix importsAlfredo Deza2013-08-162-1091/+1
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* update the requirements for ceph-restAlfredo Deza2013-08-161-1/+1
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* created the ceph-argparse packageAlfredo Deza2013-08-165-0/+1130
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* ceph-rest-api is now able to import ceph_restAlfredo Deza2013-08-161-4/+4
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* make a ceph-rest moduleAlfredo Deza2013-08-166-2/+43
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* move ceph-rest and creat the packageAlfredo Deza2013-08-166-1687/+0
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* create the rbd packageAlfredo Deza2013-08-165-0/+40
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* create the rados packageAlfredo Deza2013-08-165-0/+1688
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* move cephfs.pyAlfredo Deza2013-08-162-341/+1
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* create the cephfs packageAlfredo Deza2013-08-165-0/+380
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* add a python specific gitignoreAlfredo Deza2013-08-161-0/+34
| | | | Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
* base tox.ini file for testingAlfredo Deza2013-08-161-0/+6
| | | | Signed-off-by: Alfredo Deza <alfredo@deza.pe>
* create a MANIFEST fileAlfredo Deza2013-08-161-0/+1
| | | | Signed-off-by: Alfredo Deza <alfredo@deza.pe>
* create a setup.py fileAlfredo Deza2013-08-161-0/+32
| | | | Signed-off-by: Alfredo Deza <alfredo@deza.pe>
* Merge branch 'wip-5848-coll'David Zafman2013-08-153-3/+163
|\ | | | | | | Reviewed-by: Sage Weil <sage@inktank.com>
| * osd: Add perf tracking for all states in RecoveryStateDavid Zafman2013-08-153-3/+163
| | | | | | | | | | | | Fixes: #5848 Signed-off-by: David Zafman <david.zafman@inktank.com>
* | Merge remote-tracking branch 'gh/next'Sage Weil2013-08-1510-58/+186
|\ \
| * \ Merge pull request #506 from dmick/wip-admin-daemonSage Weil2013-08-151-18/+19
| |\ \ | | | | | | | | Reviewed-by: Sage Weil <sage@inktank.com>
| | * | ceph.in: --admin-daemon was not returning EINVAL on bad commandDan Mick2013-08-151-18/+19
| |/ / | | | | | | | | | | | | | | | | | | Fix by restructuring code to hoist common code and have only one place where admin_socket is actually called. Signed-off-by: Dan Mick <dan.mick@inktank.com>
| * | mon: use str_join instead of std::copySage Weil2013-08-152-12/+4
| | | | | | | | | | | | | | | | | | | | | The std::copy method leaves a trailing separator. Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com>
| * | config: fix stringification of config valuesSage Weil2013-08-151-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The std::copy construct leaves a trailing separator character, which breaks parsing for booleans (among other things) and probably mangles everything else too. Backport: dumpling Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Samuel Just <sam.just@inktank.com>
| * | common: add str_join helperSage Weil2013-08-151-1/+14
| | | | | | | | | | | | | | | Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Dan Mick <dan.mick@inktank.com>
| * | Revert "config: fix stringification of config values"Sage Weil2013-08-151-4/+1
| | | | | | | | | | | | | | | | | | This reverts commit fefe0c602f78e66d35fd5806da4c2e4e154a267c. I have a cleaner cleanup.
| * | config: fix stringification of config valuesSage Weil2013-08-151-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The std::copy construct leaves a trailing separator character, which breaks parsing for booleans (among other things) and probably mangles everything else too. Backport: dumpling Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Samuel Just <sam.just@inktank.com>
| * | Merge pull request #496 from ceph/wip-monstore-copySage Weil2013-08-151-3/+77
| |\ \ | | | | | | | | tools: ceph-monstore-tool: copy a store's contents to another store
| | * | tools: ceph-monstore-tool: allow copying store contents to a new locationJoao Eduardo Luis2013-08-121-3/+77
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Usage: ceph-monstore-tool --mon-store-path <in-path> --out <out-path> \ --command store-copy Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
| * | | rados.py: fix Rados() unicode checkingJosh Durgin2013-08-142-1/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Check new parameters and check that rados_id is not None again to catch the empty string. Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Sage Weil <sage.weil@inktank.com>
| * | | rados.py: fix Rados() backwards compatibilityJosh Durgin2013-08-142-2/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previously it had no name parameter, so the default will be used by old clients. However, if an old client set rados_id, a new check that both rados_id and name are set would result in an error. Fix this by only applying the default names after the check, and add tests of this behavior. This was introduced in 783b7ec847c7f987ac1814c9c41c91921cac4eba, so it does not affect cuttlefish. Fixes: #5970 Reported-by: Michael Morgan <mmorgan@dca.net> Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Sage Weil <sage.weil@inktank.com>
| * | | librados: fix async aio completion wakeupSage Weil2013-08-141-12/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For aio flush, we register a wait on the most recent write. The write completion code, however, was *only* waking the waiter if they were waiting on that write, without regard to previous writes (completed or not). For example, we might have 6 and 7 outstanding and wait on 7. If they finish in order all is well, but if 7 finishes first we do the flush completion early. Similarly, if we - start 6 - start 7 - finish 7 - flush; wait on 7 - finish 6 we can hang forever. Fix by doing any completions that are prior to the oldest pending write in the aio write completion handler. Refs: #5919 Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Tested-by: Oliver Francke <Oliver.Francke@filoo.de>
| * | | librados: fix locking for AioCompletionImpl refcountingJosh Durgin2013-08-141-5/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add an already-locked helper so that C_Aio{Safe,Complete} can increment the reference count when their caller holds the lock. C_AioCompleteAndSafe's caller is not holding the lock, so call regular get() to ensure no racing updates can occur. This eliminates all direct manipulations of AioCompletionImpl->ref, and makes the necessary locking clear. The only place C_AioCompleteAndSafe is used is in handling aio_flush_async(). This could cause a missing completion. Refs: #5919 Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Tested-by: Oliver Francke <Oliver.Francke@filoo.de>
* | | | Merge pull request #507 from ceph/wip-4635.masterJoão Eduardo Luís2013-08-156-101/+144
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | Bunch of tidying up on monitor services & fix #4635 Reviewed-by: Sage Weil <sage@inktank.com>
| * | | | PendingReleaseNotes: reflect 'osd crush set' behavior changeJoao Eduardo Luis2013-08-151-0/+8
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
| * | | | vstart.sh: s/osd crush set/osd crush add/ as it's supposed to beJoao Eduardo Luis2013-08-151-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 'osd crush set' should only be used to update already existing items on the map whereas 'osd crush add' should be able to 'add and update' items. Considering at that point we are effectively adding a new item to the crush map, use 'add' instead of 'set'. Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
| * | | | mon: OSDMonitor: don't expose uncommitted state on 'osd crush add/set'Joao Eduardo Luis2013-08-151-47/+57
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes: #4635 Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
| * | | | mon: OSDMonitor: document 'prepare_command' wrt expected behavior of no-opsJoao Eduardo Luis2013-08-151-0/+30
| | | | | | | | | | | | | | | | | | | | Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
| * | | | mon: OSDMonitor: don't expose uncommitted state on 'osd crush link'Sage Weil2013-08-151-23/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes: #4635 Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
View Lorry Controller Status